Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.093122959136963
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.162509441375732
Linear Weight Rank: 179
Intra Cos: 0.028020234778523445
Inter Cos: -0.00452499371021986
Norm Quadratic Average: 8.714689254760742
Nearest Class Center Accuracy: 0.59375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.311471939086914
Linear Weight Rank: 4
Intra Cos: 0.06610961258411407
Inter Cos: -0.01512090303003788
Norm Quadratic Average: 9.249667167663574
Nearest Class Center Accuracy: 0.899125

Output Layer:
Intra Cos: 0.6156720519065857
Inter Cos: -0.12608154118061066
Norm Quadratic Average: 5.804448127746582
Nearest Class Center Accuracy: 0.984

Test Set:
Average Loss: 0.5776909198760987
Accuracy: 0.768
NC1 Within Class Collapse: 4.114576816558838
NC2 Equinorm: Features: 0.12730886042118073, Weights: 0.04862956702709198
NC2 Equiangle: Features: 0.13982005914052328, Weights: 0.021623348196347553
NC3 Self-Duality: 0.36034271121025085
NC4 NCC Mismatch: 0.14649999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.093122959136963
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.162509441375732
Linear Weight Rank: 179
Intra Cos: 0.026928221806883812
Inter Cos: -0.003953441046178341
Norm Quadratic Average: 8.74588680267334
Nearest Class Center Accuracy: 0.585

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.311471939086914
Linear Weight Rank: 4
Intra Cos: 0.04926499351859093
Inter Cos: -0.004602125380188227
Norm Quadratic Average: 9.277212142944336
Nearest Class Center Accuracy: 0.7455

Output Layer:
Intra Cos: 0.39701345562934875
Inter Cos: -0.041897837072610855
Norm Quadratic Average: 5.6825642585754395
Nearest Class Center Accuracy: 0.765

